LLaVA-NeXT-Video-34B / config.json
ZhangYuanhan's picture
Update config.json
91b8947 verified
{
"_name_or_path": "/yi/Nous-Hermes-2-Yi-34B",
"architectures": [
"LlavaLlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 7,
"freeze_mm_mlp_adapter": false,
"freeze_mm_vision_resampler": false,
"hidden_act": "silu",
"hidden_size": 7168,
"image_aspect_ratio": "anyres",
"image_crop_resolution": 224,
"image_grid_pinpoints": [
[
336,
672
],
[
672,
336
],
[
672,
672
],
[
1008,
336
],
[
336,
1008
]
],
"image_split_resolution": 224,
"initializer_range": 0.02,
"intermediate_size": 20480,
"max_position_embeddings": 4096,
"mm_hidden_size": 1024,
"mm_patch_merge_type": "spatial_unpad",
"mm_projector_lr": null,
"mm_projector_type": "mlp2x_gelu",
"mm_resampler_type": "spatial_pool",
"mm_spatial_pool_mode": "average",
"mm_spatial_pool_out_channels": 1024,
"mm_spatial_pool_stride": 2,
"mm_use_im_patch_token": false,
"mm_use_im_start_end": false,
"mm_vision_select_feature": "patch",
"mm_vision_select_layer": -2,
"mm_vision_tower": "openai/clip-vit-large-patch14-336",
"mm_vision_tower_lr": null,
"model_type": "llava",
"num_attention_heads": 56,
"num_hidden_layers": 60,
"num_key_value_heads": 8,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 5000000.0,
"tie_word_embeddings": false,
"tokenizer_model_max_length": 8192,
"tokenizer_padding_side": "right",
"torch_dtype": "bfloat16",
"transformers_version": "4.39.0.dev0",
"tune_mm_mlp_adapter": false,
"tune_mm_vision_resampler": false,
"unfreeze_mm_vision_tower": false,
"use_cache": true,
"use_mm_proj": true,
"vocab_size": 64000
}